Landmark Screen Portal · compétence Open Skill

Landmark Screen Portal

I was practicing a choreo near the crosswalk when this travel-poster idea landed. The phone screen becomes a doorway to the landmark. It takes a description, an optional destination photo, and an optional adult photo to make a city travel ad with a headline. **tips from me:** - use a destination photo when you want a specific landmark reproduced - describe the city, headline, and how you want the screen portal to open - keep the default 3:4 ratio, or try 9:16 for a phone clip - if adding a person, use an adult photo you have the right to use, with their face preserved post what you make, I’d love to see which city lights you pick.

@AvaLindqvist

Travel

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-17/rn25h8y6.webp

# Landmark Screen Portal

The screen is just the doorway. A landmark emerges from a tilted hand-held phone and flows seamlessly into the real sky and landscape around it, with birds, a jet overhead and a crisp city headline.

## When to use

- The user wants a hyper-real travel ad where a famous landmark bursts out of a hand-held phone or tablet screen and continues seamlessly into the real landscape (screen portal travel poster, landmark out of phone ad)
- A variation on a previous result: tablet

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Destination photo | No | — | the landmark to reproduce |
| Description | Yes | — | What the user wants; merged into the prompt |
| Device | No | `smartphone` | smartphone (default), tablet |
| Ratio | No | `3:4 default` | 3:4 default; 9:16, 4:5 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Landmark Screen Portal', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
6. Reply in one or two sentences, e.g. "Done! Here's your landmark screen portal. I can also try tablet if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: a hyper-realistic travel advertisement: a hand holding a tilted glossy <device: smartphone (default) or tablet> in portrait orientation, from whose screen <landmark: the user-named landmark or from the destination photo> emerges three-dimensionally and continues seamlessly into the real landscape behind, birds in flight, a commercial airplane crossing a bright blue sky, warm natural sunlight, crisp detail, a short headline "<city name>" in bold clean lettering spelled exactly, no real brand logos on the device. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the